Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3352 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.3846. Min Act: -0.0001

Data Index: 1476931 (Python Code)

Max Activating Token Index: 451

Text #1

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.3624. Min Act: -0.0001

Data Index: 1367701 (Python Code)

Max Activating Token Index: 637

Text #2

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.3389. Min Act: -0.0001

Data Index: 1469185 (Python Code)

Max Activating Token Index: 97

Text #3

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.3351. Min Act: -0.0001

Data Index: 1466395 (Python Code)

Max Activating Token Index: 54

Text #4

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.3422. Min Act: -0.0001

Data Index: 1629454 (Python Code)

Max Activating Token Index: 96

Text #5

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.3314. Min Act: -0.0001

Data Index: 1504962 (Python Code)

Max Activating Token Index: 768

Text #6

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.2857. Min Act: -0.0001

Data Index: 1526334 (Python Code)

Max Activating Token Index: 105

Text #7

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.3042. Min Act: -0.0001

Data Index: 1371971 (Python Code)

Max Activating Token Index: 729

Text #8

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.3381. Min Act: -0.0001

Data Index: 1577258 (Python Code)

Max Activating Token Index: 14

Text #9

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.3613. Min Act: -0.0001

Data Index: 1591462 (Python Code)

Max Activating Token Index: 627

Text #10

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.3514. Min Act: -0.0001

Data Index: 1586416 (Python Code)

Max Activating Token Index: 757

Text #11

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.3022. Min Act: -0.0001

Data Index: 1623205 (Python Code)

Max Activating Token Index: 115

Text #12

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.2864. Min Act: -0.0001

Data Index: 1476034 (Python Code)

Max Activating Token Index: 956

Text #13

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.3303. Min Act: -0.0001

Data Index: 1363775 (Python Code)

Max Activating Token Index: 24

Text #14

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.2941. Min Act: -0.0001

Data Index: 1441410 (Python Code)

Max Activating Token Index: 128

Text #15

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.2931. Min Act: -0.0001

Data Index: 1427160 (Python Code)

Max Activating Token Index: 480

Text #16

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.3259. Min Act: -0.0001

Data Index: 1556418 (Python Code)

Max Activating Token Index: 96

Text #17

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.3143. Min Act: -0.0001

Data Index: 1634840 (Python Code)

Max Activating Token Index: 12

Text #18

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.3020. Min Act: -0.0001

Data Index: 1639661 (Python Code)

Max Activating Token Index: 489

Text #19

Max Range: 0.3846. Min Range: -0.3846

Max Act: 0.2885. Min Act: -0.0001

Data Index: 1364668 (Python Code)

Max Activating Token Index: 598